首页|Data on Machine Learning Reported by Heiko Holz and Colleagues (Performance Diff erences of a Touch-Based Serial Reaction Time Task in Healthy Older Participants and Older Participants With Cognitive Impairment on a Tablet: Experimental Stud y)
Data on Machine Learning Reported by Heiko Holz and Colleagues (Performance Diff erences of a Touch-Based Serial Reaction Time Task in Healthy Older Participants and Older Participants With Cognitive Impairment on a Tablet: Experimental Stud y)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating from Tubingen, Ge rmany, by NewsRx correspondents, research stated, "Digital neuropsychological to ols for diagnosing neurodegenerative diseases in the older population are becomi ng more relevant and widely adopted because of their diagnostic capabilities. In this context, explicit memory is mainly examined." Our news editors obtained a quote from the research, "The assessment of implicit memory occurs to a lesser extent. A common measure for this assessment is the s erial reaction time task (SRTT). This study aims to develop and empirically test a digital tablet-based SRTT in older participants with cognitive impairment (Co I) and healthy control (HC) participants. On the basis of the parameters of resp onse accuracy, reaction time, and learning curve, we measure implicit learning a nd compare the HC and CoI groups. A total of 45 individuals (n=27, 60% HCs and n=18, 40% participants with CoI-diagnosed by an interdisci plinary team) completed a tablet-based SRTT. They were presented with 4 blocks o f stimuli in sequence and a fifth block that consisted of stimuli appearing in r andom order. Statistical and machine learning modeling approaches were used to i nvestigate how healthy individuals and individuals with CoI differed in their ta sk performance and implicit learning. Linear mixed-effects models showed that in dividuals with CoI had significantly higher error rates (b=-3.64, SE 0.86; z=-4. 25; P<.001); higher reaction times (F=22.32; P<.001); and lower implicit learning, measured via the response increase between s equence blocks and the random block (b=-0.34; SE 0.12; t=-2.81; P=.007). Further more, machine learning models based on these findings were able to reliably and accurately predict whether an individual was in the HC or CoI group, with an ave rage prediction accuracy of 77.13% (95% CI 74.67% -81.33%). Our results showed that the HC and CoI groups differed su bstantially in their performance in the SRTT. This highlights the promising pote ntial of implicit learning paradigms in the detection of CoI."
TubingenGermanyEuropeCyborgsEmer ging TechnologiesMachine Learning
NETL
NSTL
